2.0

.idea/.gitignore

@@ -0,0 +1,5 @@
+# 默认忽略的文件
+/shelf/
+/workspace.xml
+# 基于编辑器的 HTTP 客户端请求
+/httpRequests/

.idea/ailai_image_obb.iml

@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="yolov11" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.10" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="yolov11" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/ailai_image_obb.iml" filepath="$PROJECT_DIR$/.idea/ailai_image_obb.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

ailai_pc/detect.py

@@ -0,0 +1,134 @@
+import cv2
+import numpy as np
+from rknnlite.api import RKNNLite
+
+MODEL_PATH = "detect.rknn"
+CLASS_NAMES = ["bag"]  # 单类
+
+
+class Yolo11Detector:
+    def __init__(self, model_path):
+        self.rknn = RKNNLite(verbose=False)
+
+        # 加载 RKNN 模型
+        ret = self.rknn.load_rknn(model_path)
+        assert ret == 0, "❌ Load RKNN model failed"
+
+        # 初始化运行时（使用 NPU 核心0）
+        ret = self.rknn.init_runtime(core_mask=RKNNLite.NPU_CORE_0)
+        assert ret == 0, "❌ Init runtime failed"
+
+        # 模型输入大小
+        self.input_size = 640
+        # YOLO anchors（根据你训练的模型）
+        self.anchors = {
+            8: [[10, 13], [16, 30], [33, 23]],
+            16: [[30, 61], [62, 45], [59, 119]],
+            32: [[116, 90], [156, 198], [373, 326]]
+        }
+
+    def preprocess(self, img):
+        """高性能预处理：缩放+RGB"""
+        h, w = img.shape[:2]
+        scale = min(self.input_size / w, self.input_size / h)
+        new_w, new_h = int(w * scale), int(h * scale)
+        img_resized = cv2.resize(img, (new_w, new_h))
+        canvas = np.full((self.input_size, self.input_size, 3), 114, dtype=np.uint8)
+        dw, dh = (self.input_size - new_w) // 2, (self.input_size - new_h) // 2
+        canvas[dh:dh + new_h, dw:dw + new_w, :] = img_resized
+        img_rgb = cv2.cvtColor(canvas, cv2.COLOR_BGR2RGB)
+        return np.expand_dims(img_rgb, 0).astype(np.uint8), scale, dw, dh
+
+    def postprocess(self, outputs, scale, dw, dh, conf_thresh=0.25, iou_thresh=0.45):
+        """解析 YOLO 输出"""
+        # 注意：根据 RKNN 输出节点选择
+        preds = outputs[0].reshape(-1, outputs[0].shape[1])  # 假设输出 [1, N, C]
+        boxes, scores, class_ids = [], [], []
+
+        for p in preds:
+            conf = p[4]
+            if conf < conf_thresh:
+                continue
+            cls_conf = p[5]  # 单类模型
+            score = conf * cls_conf
+            if score < conf_thresh:
+                continue
+            cx, cy, w, h = p[:4]
+            x1 = (cx - w / 2 - dw) / scale
+            y1 = (cy - h / 2 - dh) / scale
+            x2 = (cx + w / 2 - dw) / scale
+            y2 = (cy + h / 2 - dh) / scale
+            boxes.append([x1, y1, x2, y2])
+            scores.append(score)
+            class_ids.append(0)  # 单类
+
+        if len(boxes) == 0:
+            return []
+
+        boxes = np.array(boxes)
+        scores = np.array(scores)
+        class_ids = np.array(class_ids)
+
+        # 简单 NMS
+        idxs = np.argsort(scores)[::-1]
+        keep = []
+        while len(idxs) > 0:
+            i = idxs[0]
+            keep.append(i)
+            if len(idxs) == 1:
+                break
+            x1, y1, x2, y2 = boxes[i]
+            xx1 = np.maximum(x1, boxes[idxs[1:], 0])
+            yy1 = np.maximum(y1, boxes[idxs[1:], 1])
+            xx2 = np.minimum(x2, boxes[idxs[1:], 2])
+            yy2 = np.minimum(y2, boxes[idxs[1:], 3])
+            inter = np.maximum(0, xx2 - xx1) * np.maximum(0, yy2 - yy1)
+            area_i = (x2 - x1) * (y2 - y1)
+            area_j = (boxes[idxs[1:], 2] - boxes[idxs[1:], 0]) * (boxes[idxs[1:], 3] - boxes[idxs[1:], 1])
+            iou = inter / (area_i + area_j - inter + 1e-6)
+            idxs = idxs[1:][iou < iou_thresh]
+
+        results = []
+        for i in keep:
+            results.append({
+                "box": boxes[i],
+                "score": scores[i],
+                "class_id": class_ids[i]
+            })
+        return results
+
+    def detect(self, img):
+        img_data, scale, dw, dh = self.preprocess(img)
+        outputs = self.rknn.inference([img_data])
+        results = self.postprocess(outputs, scale, dw, dh)
+        return results
+
+    def release(self):
+        self.rknn.release()
+
+
+if __name__ == "__main__":
+    detector = Yolo11Detector(MODEL_PATH)
+    cap = cv2.VideoCapture(0)  # 可以换成图片路径
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        results = detector.detect(frame)
+
+        for r in results:
+            x1, y1, x2, y2 = map(int, r["box"])
+            cls_id = r["class_id"]
+            score = r["score"]
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+            cv2.putText(frame, f"{CLASS_NAMES[cls_id]} {score:.2f}", (x1, y1 - 10),
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
+
+        cv2.imshow("YOLOv11 Detection", frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    detector.release()
+    cap.release()

ailai_pc/detet_pc.py

@@ -0,0 +1,72 @@
+# detect_pt.py
+import cv2
+import torch
+from ultralytics import YOLO
+
+# ======================
+# 配置参数
+# ======================
+MODEL_PATH = 'best.pt'           # 你的训练模型路径（yolov8n.pt 或你自己训练的）
+#IMG_PATH = '/home/hx/开发/ailai_image_obb/ailai_pc/train/192.168.0.234_01_202510141514352.jpg'            # 测试图像路径
+IMG_PATH = '1.jpg'
+OUTPUT_PATH = '/home/hx/开发/ailai_image_obb/ailai_pc/output_pt.jpg'    # 可视化结果保存路径
+CONF_THRESH = 0.5                # 置信度阈值
+CLASS_NAMES = ['bag']          # 你的类别名列表（按训练时顺序）
+
+# 是否显示窗口（适合有 GUI 的 PC）
+SHOW_IMAGE = True
+
+# ======================
+# 主函数
+# ======================
+def main():
+    # 检查 CUDA
+    device = 'cuda' if torch.cuda.is_available() else 'cpu'
+    print(f"✅ 使用设备: {device}")
+
+    # 加载模型
+    print("➡️  加载 YOLO 模型...")
+    model = YOLO(MODEL_PATH)  # 自动加载架构和权重
+    model.to(device)
+
+    # 推理
+    print("➡️  开始推理...")
+    results = model(IMG_PATH, imgsz=640, conf=CONF_THRESH, device=device)
+
+    # 获取第一张图的结果
+    r = results[0]
+
+    # 获取原始图像（BGR）
+    img = cv2.imread(IMG_PATH)
+    if img is None:
+        raise FileNotFoundError(f"无法读取图像: {IMG_PATH}")
+
+    print("\n📋 检测结果:")
+    for box in r.boxes:
+        # 获取数据
+        xyxy = box.xyxy[0].cpu().numpy()  # [x1, y1, x2, y2]
+        conf = box.conf.cpu().numpy()[0]  # 置信度
+        cls_id = int(box.cls.cpu().numpy()[0])  # 类别 ID
+        cls_name = CLASS_NAMES[cls_id]         # 类别名
+
+        x1, y1, x2, y2 = map(int, xyxy)
+        print(f"  类别: {cls_name}, 置信度: {conf:.3f}, 框: [{x1}, {y1}, {x2}, {y2}]")
+
+        # 画框
+        cv2.rectangle(img, (x1, y1), (x2, y2), (0, 255, 0), 2)
+        # 画标签
+        label = f"{cls_name} {conf:.2f}"
+        cv2.putText(img, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
+
+    # 保存结果
+    cv2.imwrite(OUTPUT_PATH, img)
+    print(f"\n🖼️  可视化结果已保存: {OUTPUT_PATH}")
+
+    # 显示（可选）
+    if SHOW_IMAGE:
+        cv2.imshow("YOLOv8 Detection", img)
+        cv2.waitKey(0)
+        cv2.destroyAllWindows()
+
+if __name__ == '__main__':
+    main()

main/README.md

@@ -26,7 +26,7 @@
 pip install opencv-python numpy rknnlite
 ```
 
-## 函数调用
+## 函数调用1.0
 
 您也可以直接调用 calculate_offset_from_image 函数，以便集成到其他项目中：
 示例 1: 仅获取偏移量（不画图）
@@ -46,11 +46,53 @@ from calculate_offset import calculate_offset_from_image
 result = calculate_offset_from_image("your_image_path.jpg", visualize=True)
 ```
 
-该函数返回一个包含下列字段的字典：
+## 函数调用2.0
+
+示例 1: 仅获取偏移量（不画图）
+
+```bash
+from caculate_diff2.0 import calculate_offset_from_image
+
+result = calculate_offset_from_image("11.jpg", visualize=False)
+if result['success']:
+    print(f"Offset: DeltaX={result['dx_mm']:+.2f} mm, DeltaY={result['dy_mm']:+.2f} mm")
+else:
+    print("Error:", result['message'])
+
+```
+示例 2: 获取偏移量并保存可视化图
+
+```bash
+from caculate_diff2.0 import calculate_offset_from_image
+
+result = calculate_offset_from_image("11.jpg", visualize=True)
+
+```
+
+##该函数返回一个包含下列字段的字典1.0：
 
     success: 成功标志（True/False）
     dx_mm: 水平偏移（毫米）
     dy_mm: 垂直偏移（毫米）
     cx: 中心点 x 坐标（像素）
     cy: 中心点 y 坐标（像素）
-    message: 错误信息或成功提示
+<<<<<<< HEAD
+    message: 错误信息或成功提示
+    
+##该函数返回一个包含下列字段的字典2.0：
+
+    success: 成功标志（True/False）
+    dx_mm: 水平偏移（毫米）
+    dy_mm: 垂直偏移（毫米）
+    cx: 中心点 x 坐标（像素）
+    cy: 中心点 y 坐标（像素）
+    message: 错误信息或成功提示
+    class_id: 检测类别 ID  #这里是bag的id是0
+    obj_conf: 检测置信度   #这就是识别为料袋的置信度
+    bbox: 检测矩形框 [x_left, y_top, width, height]
+    message: 错误信息或成功提示
+
+
+=======
+    message: 错误信息或成功提示
+>>>>>>> a6505573b9361ce4ab920ddc55f4bc6d86d7dfb4

main/caculate_diff2.0.py

@@ -0,0 +1,235 @@
+import cv2
+import numpy as np
+import os
+from rknnlite.api import RKNNLite
+
+# ====================== 配置区 ======================
+MODEL_PATH = "point.rknn"
+OUTPUT_DIR = "./output_rknn"
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+# 固定参考点（像素坐标）
+FIXED_REF_POINT = (535, 605)
+
+# mm/px 缩放因子（根据标定数据填写）
+width_mm = 70.0
+width_px = 42
+SCALE_X = width_mm / float(width_px)
+height_mm = 890.0
+height_px = 507
+SCALE_Y = height_mm / float(height_px)
+print(f"Scale factors: SCALE_X={SCALE_X:.3f} mm/px, SCALE_Y={SCALE_Y:.3f} mm/px")
+
+# 输入尺寸
+IMG_SIZE = (640, 640)
+
+
+def letterbox_resize(image, size, bg_color=114):
+    target_w, target_h = size
+    h, w = image.shape[:2]
+    scale = min(target_w / w, target_h / h)
+    new_w, new_h = int(w * scale), int(h * scale)
+    resized = cv2.resize(image, (new_w, new_h))
+    canvas = np.full((target_h, target_w, 3), bg_color, dtype=np.uint8)
+    dx, dy = (target_w - new_w) // 2, (target_h - new_h) // 2
+    canvas[dy:dy + new_h, dx:dx + new_w] = resized
+    return canvas, scale, dx, dy
+
+
+def safe_sigmoid(x):
+    x = np.clip(x, -50, 50)
+    return 1.0 / (1.0 + np.exp(-x))
+
+
+def softmax(x):
+    x = x - np.max(x)
+    e = np.exp(x)
+    return e / e.sum()
+
+
+def dfl_to_xywh(loc, grid_x, grid_y, stride):
+    """将 DFL 输出解析为 xywh"""
+    xywh_ = np.zeros(4)
+    xywh = np.zeros(4)
+
+    # 每个维度 16 bins 做 softmax
+    for i in range(4):
+        l = loc[i * 16:(i + 1) * 16]
+        l = softmax(l)
+        xywh_[i] = sum([j * l[j] for j in range(16)])
+
+    # 对应公式
+    xywh_[0] = (grid_x + 0.5) - xywh_[0]
+    xywh_[1] = (grid_y + 0.5) - xywh_[1]
+    xywh_[2] = (grid_x + 0.5) + xywh_[2]
+    xywh_[3] = (grid_y + 0.5) + xywh_[3]
+
+    # 转成中心点 + 宽高
+    xywh[0] = ((xywh_[0] + xywh_[2]) / 2) * stride
+    xywh[1] = ((xywh_[1] + xywh_[3]) / 2) * stride
+    xywh[2] = (xywh_[2] - xywh_[0]) * stride
+    xywh[3] = (xywh_[3] - xywh_[1]) * stride
+
+    # 转为左上角坐标
+    xywh[0] = xywh[0] - xywh[2] / 2
+    xywh[1] = xywh[1] - xywh[3] / 2
+    return xywh
+
+
+def parse_pose_outputs(outputs, conf_threshold=0.5, dx=0, dy=0, scale=1.0):
+    """
+    完整解析 RKNN YOLO-Pose 输出
+    返回 keypoints, class_id, obj_conf, bbox（已映射回原图）
+    """
+    boxes = []
+    obj_confs = []
+    class_ids = []
+
+    # 遍历前三个输出 tensor (det 输出)
+    for idx in range(3):
+        det = np.array(outputs[idx])[0]  # (C,H,W)
+        C, H, W = det.shape
+        num_classes = C - 64  # 前64通道为 DFL bbox
+        stride = 640 // H
+
+        for h in range(H):
+            for w in range(W):
+                for c in range(num_classes):
+                    conf = safe_sigmoid(det[64 + c, h, w])
+                    if conf >= conf_threshold:
+                        loc = det[:64, h, w].astype(np.float32)
+                        xywh = dfl_to_xywh(loc, w, h, stride)
+                        boxes.append(xywh)
+                        obj_confs.append(conf)
+                        class_ids.append(c)
+
+    if not obj_confs:
+        best_box = np.array([0, 0, 0, 0])
+        class_id = -1
+        obj_conf = 0.0
+    else:
+        max_idx = np.argmax(obj_confs)
+        best_box = boxes[max_idx]
+        class_id = class_ids[max_idx]
+        obj_conf = obj_confs[max_idx]
+
+    # 🔹 bbox 坐标映射回原图
+    x, y, w, h = best_box
+    x = (x - dx) / scale
+    y = (y - dy) / scale
+    w = w / scale
+    h = h / scale
+    best_box = np.array([x, y, w, h])
+
+    # 🔹 关键点解析
+    kpt_output = np.array(outputs[3])[0]  # (num_kpts, 3, num_anchor)
+    confs = kpt_output[:, 2, :]
+    best_anchor_idx = np.argmax(np.mean(confs, axis=0))
+    kpt_data = kpt_output[:, :, best_anchor_idx]
+
+    keypoints = []
+    for i in range(kpt_data.shape[0]):
+        x_img, y_img, vis_conf_raw = kpt_data[i]
+        vis_prob = safe_sigmoid(vis_conf_raw)
+        x_orig = (x_img - dx) / scale
+        y_orig = (y_img - dy) / scale
+        keypoints.append([x_orig, y_orig, vis_prob])
+
+    return np.array(keypoints), class_id, obj_conf, best_box
+
+
+def compute_offset(keypoints, fixed_point, scale_x, scale_y):
+    if len(keypoints) < 2:
+        return None
+    p1, p2 = keypoints[0], keypoints[1]
+    cx = (p1[0] + p2[0]) / 2.0
+    cy = (p1[1] + p2[1]) / 2.0
+    dx_mm = (cx - fixed_point[0]) * scale_x
+    dy_mm = (cy - fixed_point[1]) * scale_y
+    return cx, cy, dx_mm, dy_mm
+
+
+def visualize_result(image, keypoints, bbox, fixed_point, offset_info, save_path):
+    vis = image.copy()
+    colors = [(0, 0, 255), (0, 255, 255)]
+    cx, cy, dx_mm, dy_mm = offset_info
+    fx, fy = map(int, fixed_point)
+
+    # 绘制关键点
+    for i, (x, y, conf) in enumerate(keypoints[:2]):
+        if conf > 0.5:
+            cv2.circle(vis, (int(x), int(y)), 6, colors[i], -1)
+    if len(keypoints) >= 2:
+        cv2.line(vis,
+                 (int(keypoints[0][0]), int(keypoints[0][1])),
+                 (int(keypoints[1][0]), int(keypoints[1][1])),
+                 (0, 255, 0), 2)
+
+    # 绘制 bbox
+    x, y, w, h = bbox
+    cv2.rectangle(vis, (int(x), int(y)), (int(x + w), int(y + h)), (255, 0, 0), 2)
+
+    # 绘制中心点
+    cv2.circle(vis, (int(cx), int(cy)), 10, (0, 255, 0), 3)
+    cv2.circle(vis, (fx, fy), 12, (255, 255, 0), 3)
+    cv2.arrowedLine(vis, (fx, fy), (int(cx), int(cy)), (255, 255, 0), 2, tipLength=0.05)
+    cv2.putText(vis, f"DeltaX={dx_mm:+.1f}mm", (fx + 30, fy - 30),
+                cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 255), 2)
+    cv2.putText(vis, f"DeltaY={dy_mm:+.1f}mm", (fx + 30, fy + 30),
+                cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 255), 2)
+
+    cv2.imwrite(save_path, vis)
+
+
+def calculate_offset_from_image(image_path, visualize=False):
+    orig = cv2.imread(image_path)
+    if orig is None:
+        return {'success': False, 'message': f'Failed to load image: {image_path}'}
+
+    img_resized, scale, dx, dy = letterbox_resize(orig, IMG_SIZE)
+    infer_img = np.expand_dims(img_resized[..., ::-1], 0).astype(np.uint8)
+
+    rknn = RKNNLite(verbose=False)
+    ret = rknn.load_rknn(MODEL_PATH)
+    if ret != 0:
+        return {'success': False, 'message': 'Failed to load RKNN model'}
+
+    try:
+        rknn.init_runtime(core_mask=RKNNLite.NPU_CORE_0)
+        outputs = rknn.inference([infer_img])
+    finally:
+        rknn.release()
+
+    try:
+        keypoints, class_id, obj_conf, bbox = parse_pose_outputs(outputs, dx=dx, dy=dy, scale=scale)
+    except Exception as e:
+        return {'success': False, 'message': f'Parse error: {str(e)}'}
+
+    offset_info = compute_offset(keypoints, FIXED_REF_POINT, SCALE_X, SCALE_Y)
+    if offset_info is None:
+        return {'success': False, 'message': 'Not enough keypoints'}
+
+    cx, cy, dx_mm, dy_mm = offset_info
+
+    if visualize:
+        vis_save_path = os.path.join(OUTPUT_DIR, f"result_{os.path.basename(image_path)}")
+        visualize_result(orig, keypoints, bbox, FIXED_REF_POINT, offset_info, vis_save_path)
+
+    return {'success': True, 'dx_mm': dx_mm, 'dy_mm': dy_mm,
+            'cx': cx, 'cy': cy, 'class_id': class_id,
+            'obj_conf': obj_conf, 'bbox': bbox,
+            'message': 'Success'}
+
+
+# ====================== 使用示例 ======================
+if __name__ == "__main__":
+    image_path = "11.jpg"
+    result = calculate_offset_from_image(image_path, visualize=True)
+
+    if result['success']:
+        print(f"Center point: ({result['cx']:.1f}, {result['cy']:.1f})")
+        print(f"Offset: DeltaX={result['dx_mm']:+.2f} mm, DeltaY={result['dy_mm']:+.2f} mm")
+        print(f"Class ID: {result['class_id']}, Confidence: {result['obj_conf']:.3f}")
+        print(f"BBox: {result['bbox']}")
+    else:
+        print("Error:", result['message'])